# Machine Translation Evaluation on WMT De→En 2019 (Top 30%)

Source: [Machine Translation Evaluation on WMT De→En 2019 (Top 30%)](<https://www.sota2.com/research/sota/machine-translation-evaluation-on-wmt-de-en-2019-top-30-percent>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:57:42.833Z

Evaluation of German-to-English Machine Translation performance on the WMT 2019 dataset, restricted to the Top 30% subset, measured using correlation metrics (\|r\|, \|τ\|, ρ).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Machine Translation Evaluation |
| Dataset (including any stated split) | WMT De→En Top 30% 2019 |
| Metric | Pearson Correlation (\|r\|) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Pearson Correlation (\|r\|)](<https://www.sota2.com/research/sota/machine-translation-evaluation-on-wmt-de-en-2019-top-30-percent.md?metric=Pearson%20Correlation%20(%7Cr%7C)>): Higher is better; unit: SCALAR.

- [Kendall's Tau (\|τ\|)](<https://www.sota2.com/research/sota/machine-translation-evaluation-on-wmt-de-en-2019-top-30-percent.md?metric=Kendall%27s%20Tau%20(%7C%CF%84%7C)>): Higher is better; unit: SCALAR.

- [Spearman's Rho (ρ)](<https://www.sota2.com/research/sota/machine-translation-evaluation-on-wmt-de-en-2019-top-30-percent.md?metric=Spearman%27s%20Rho%20(%CF%81)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Pearson Correlation (\|r\|) | Result date | Report paper |
| --- | --- | --- | --- |
| TER | 0.883 | Not recorded | 68fa6a711e209131cea2820c |
| BLEU | 0.808 | Not recorded | 68fa6a711e209131cea2820c |
| DA-BERTScore | 0.693 | Not recorded | 68fa6a711e209131cea2820c |
| METEOR | 0.632 | Not recorded | 68fa6a711e209131cea2820c |
| BERTScore | 0.271 | Not recorded | 68fa6a711e209131cea2820c |

### TER

Pearson Correlation (\|r\|): 0.883. Result ID: 698e3487ffc3901de09ba753.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a711e209131cea2820c.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### BLEU

Pearson Correlation (\|r\|): 0.808. Result ID: 698e3487ffc3901de09ba752.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a711e209131cea2820c.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DA-BERTScore

Pearson Correlation (\|r\|): 0.693. Result ID: 698e3487ffc3901de09ba756.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a711e209131cea2820c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a711e209131cea2820c.md>)

[Implementation](<https://github.com/NLP2CT/Difficulty-Aware-MT-Evaluation>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### METEOR

Pearson Correlation (\|r\|): 0.632. Result ID: 698e3487ffc3901de09ba754.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a711e209131cea2820c.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### BERTScore

Pearson Correlation (\|r\|): 0.271. Result ID: 698e3487ffc3901de09ba755.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a711e209131cea2820c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67171e209131cea140d5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.